Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix missing normalize_embeddings argument #3201

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Fix missing normalize_embeddings argument #3201

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
79cbc90
fixed normalize_embeddings when Normalize presented in modules
BioMikeUkr Jan 28, 2025
23b6c0f
Add missing normalize_embeddings to kwargs
werent4 Jan 28, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions sentence_transformers/SentenceTransformer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -526,6 +526,7 @@ def encode(
print(embeddings.shape)
# (3, 768)
"""
kwargs["normalize_embeddings"] = normalize_embeddings
if self.device.type == "hpu" and not self.is_hpu_graph_enabled:
import habana_frameworks.torch as ht

Expand Down Expand Up @@ -685,6 +686,8 @@ def forward(self, input: dict[str, Tensor], **kwargs) -> dict[str, Tensor]:
return super().forward(input)

for module_name, module in self.named_children():
if not kwargs.get("normalize_embeddings", False) and isinstance(module, Normalize):
return input
module_kwarg_keys = self.module_kwargs.get(module_name, [])
module_kwargs = {key: value for key, value in kwargs.items() if key in module_kwarg_keys}
input = module(input, **module_kwargs)
Expand Down